jboss10··on Qwen 3.6 27B is the sweet spot for local developmentFor the 35B model, ofloading to RAM doesn't slow it down much. If you have a nice CPU and a weak GPU, it will be fast enough to use.
jboss10··on Qwen 3.6 27B is the sweet spot for local developmenthttps://unsloth.ai/docs/models/qwen3.6 And https://huggingface.co/collections/unsloth/qwen36
jboss10··on Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?Have you tried qwen3.6 or pi?
jboss10··on Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?llama.cpp It's faster and more open source. Ollama has some mixed history. I use llama-swap to emulate the Ollama experience.